**5. Patient personalisation and explanation**

Most of the previously published studies in diabetes prediction have tended to focus on all patients as one integrated database rather than separating patients [16]. It can be challenging to stratify patients based on their longitudinal data in order to determine what is triggering the visible patterns that may be specific to one cohort of patients. There is some research, such as [55] that assesses the disease prediction performance based upon different IDA techniques. For example, the onset of the disease is modelled in [56] while other studies focus on patient modelling [57]. The approach described in this chapter aims to personalise patients by using unsupervised methodologies to group time-series patient data.

The proposed descriptive strategy in this chapter has been regarded as a useful

order to implement the principles and these assumptions. It seemed to be evident

In order to introduce a different perspective on Deep Learning models' interpretability, Zintgra and co-authors [50] conducted a study to simplify the black box structure of Artificial Neural Networks (ANNs). They made use of prototypic examples method that indicate tools in order to diagnose trained ANNs. In general, ANNs analyse discrete decision-making processes and obtain high-performance

The prototype examples may be computationally intractable, including a pre-determined normal distribution to prevent the proliferation of unreasonable prototype cases. They provided an explanation of tools to train ANNs based on two datasets. Moreover, it can often be like such a losing battle to describe precisely how ANNs operate mathematically. Therefore, a much more comprehensive preprocessing methodology could also be used in a related development (e.g., generative adversarial network proposed by Goodfellow et al. in [49]). Furthermore, experimental results and hypotheses in ANNs were portrayed and tested only on two datasets. Alternatively, a more detailed analysis is required to rely on the empirical results, which might be achieved by including rich data containing imbalance issue, different types of features. Selection bias was another potential concern because it could involve possible measurement errors. It could be extended through more set of data with various features. Finally, conclusions and interpretations of data were drawn from an inevitably subjective mechanism on the investigator's basis. This was because to examine whether the produced case studies should satisfy the investigator's standards about the phenomena of been modelled (e.g., decisions could be only made by the time it came). This was established based on approaches or standards for collecting and analysing concepts that might be more unbiased. As a result, this could also enable investigators/analysers to understand the implications and weaknesses of the use of ANNs for the discrete decisionmaking process, which might enhance the strictness of the approach. However, many healthcare methods are required to reconstruct conventional prediction methods (e.g., the identification of cancers), but so far, different ideas to interpret

For the time being, the possibility of an AI physician planning to roll new prognosis without direct human intervention is a significant distance in which the more presumably in decades rather than a few years later. Recent developments in several technologies in the Deep Learning area have been powered by the steadily declining expense of computing and storage. That being said, realistic apps, includ-

explainability issues for Deep Learning in the black box resource-limited environments. Liu et al. in [51] introduced the leading solution to address these issues where a deteriorated image of Binary Convolutionary Networks caused by binarising Filtres. They offered a range of Circulant Filtres (CiFs) and a Circulant Binary Convolution (CBConv) to strengthen efficiency and to tackle those limitations for Binary Convolutionary functionalities through their proposed Circulant Backpropagation (CBP). Then, CiFs effortlessly was integrated into the current deep neural networks (DCNNs). Enormous research has indicated that perhaps the output difference among one-bit and total-precision DCNNs could be reduced by

ing certain integrated smartphone and electronic devices, have intensified

that their approach was overconfident and yet to be trusted.

*4.1.2 Prototyping examples in Artificial Neural Networks*

*Type 2 Diabetes - From Pathophysiology to Cyber Systems*

previous clinical records have been discovered.

*4.1.3 Visualisation in deep learning*

**206**

prediction results.

tool known as association rules to detect interesting relationships among T2DM complications.

attempts to address this issue and present an informative rules/ordering pattern of patient behaviour, with an aim to capture the complexities of the associated complications' over time. The proposed descriptive strategy has been regarded as a useful tool known as association rules (ARs) to detect interesting relationships

*Predicting Type 2 Diabetes Complications and Personalising Patient Using Artificial…*

Temporal Association Rules (TARs) [65] is an extension to association rules [66] to analyse basket data that includes a temporal dimension to order related items. Many algorithms with temporal rules work by dividing the temporal transitions database into different partitions based on the time granularity obliged. For example, different mining algorithms were reformulated and presented to reflect the new general temporal association rules. These include Progressive Partition Minder (PPM), Segmented Progressive Filter (SPF), and TAR algorithm [65–67]. Various algorithms have been proposed for the incremental mining of temporal association rules, especially for numerical attributes [68]. Allen's rules [69] generalised abstracted time-series data into a relation (PRECEDES) to find TARs in [70]. Various ways were proposed to explore the problem of temporal association rules discovery [71]. Nevertheless, previous studies performed discovering association rules on a given subset specified by the time [72], whilst not considering the specific

Association Rule Mining (ARM) finds frequent patterns by mining ARs with the use of two basic parameters of support and confidence [73]. The majority of the previous ARM algorithms worked by dividing the temporal transitions database

Difficulties arise with TARs when there are some rare rules of particular interest [74]. Many studies have employed the most common filtering metrics rather than support and confidence in order to detect interesting rules [75]. There is a controversy to this, as a study in the literature argued that a conservative ARM methodology only based on a fixed and rigid threshold for the filtering metrics could be problematic. A few studies attempted to mine frequent underlying patterns of diabetic complications [76]. The frequent pattern mining research significantly affects data mining techniques in longitudinal data. A post-processing approach in [77] attempted to extract interesting subsets of temporal rules within T2DM data. However, it only considered characteristic patterns of administrative data without the appearance of latent variables. Other researchers have undertaken association rule mining of clinical data [78, 79]. Lee et al. attempted to address the issue in [67] and have led to the proposal of the concept of general TARs, where the items were allowed to have varying exhibition periods, and their support was made based on that accordingly. Another research conducted by Plasse et al. in [80] looked at finding homogeneous groups of variables. They suggested that a variable clustering method could be applied to the data in order to achieve a better result in pattern discovering methodology. However, their strategy to mine ARs differed from this chapter in which the number of rules was reduced only based on hierarchical clustering applied to items, not to multiple identical binary attributes. Among these, some methods uncovered temporal patterns and relationships among clinical variables, including causal information [81], numeric time-series analysis [82]. Nevertheless, considering all of this evidence, none of the above studies has clustered uneven time-series clinical data based on a hidden variable for extracting temporal phenotype and behaviours of patients.

This chapter, so far, has described the research gap in the modelling and explaining of complex disease processes and thus given the motivation behind the

into different partitions based on the time granularity obliged.

among T2DM complications.

*DOI: http://dx.doi.org/10.5772/intechopen.94228*

exhibition period of the elements.

**6. The suggested methodology**

**209**
